bidi2pdf 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a67b40e096dd2b6b73fa65cec7d9d75182b995435c17186d755f89efebb2ab26
-  data.tar.gz: fde0861d58dd30788aa1b54a24d956d3438bd83cc08a5ec9d22e6750a3e646d6
+  metadata.gz: dbc473cb8b54517914bfa958b1925d97db54ab3e6ee640a28101b48346077192
+  data.tar.gz: 76c2d11f399a33a932f66348cfc3aad9d0c80f1e15407566b10d16a646b17d1c
 SHA512:
-  metadata.gz: 52e199c72b902e046140e6d47a9b00a8354e53a88f3af6135f0d7ab587c7d59532a904388e4a62ed4ba29c03609eab3b8c7f3aea0aa131ba8880f8ecb6f9a503
-  data.tar.gz: a83f7091a455e5c8cb5f2b7e8e621c044b2184c2c6e5a6e11aaa4f4ca2f9879ada89eb7951e7ad78e07a2d473396bb529ce5c4dfc771130a40a1977bb6e60575
+  metadata.gz: eb72b6bc4eeb2a65172c37138be3f2af5129a046a217acaf90236532c323547e0f1456f7743c509015808389da586b145cd069a26a85bbc35278c44cfea32249
+  data.tar.gz: e3b6d68003a6419e86fa33a68b51c065d7d60f95cc7bf657b12cb13ed5bef085938599b5387aca641b1a699ec47fab6804e300892b962a842d06748b061a1e5d

data/.rubocop.yml

@@ -45,6 +45,9 @@ Gemspec/DevelopmentDependencies:
 RSpec/InstanceVariable:
   Enabled: false
 
+RSpec/BeforeAfterAll:
+  Enabled: false
+
 plugins:
   - rubocop-rake
   - rubocop-rspec

data/CHANGELOG.md

@@ -1,8 +1,34 @@
-## [Unreleased]
+<!-- generated by git-cliff start -->
+
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+<!-- generated by git-cliff end -->
+
+## [0.1.2] - 2025-04-05
+
+### 🔄 Changed
+
+- Enhance CLI with YAML configuration support and additional options by @dieter-medium
+
+### 🚀 Added
+
+- Add CLI tests for rendering and configuration options by @dieter-medium
+- Add RSpec test for Bidi2pdf version number by @dieter-medium
+- Add PDF rendering test with custom print parameters and debug output by @dieter-medium
+- Add be_alive_process matcher and chromedriver manager specs for process management by @dieter-medium
+- Add RBS type signatures for Bidi2pdf classes and modules by @dieter-medium
+- Add build status badge to README by @dieter-medium
+- Add badges for maintainability, gem version, and test coverage in README by @dieter-medium
+- Add Code Climate coverage reporting to CI workflow by @dieter-medium
+- Add support for remote ChromeDriver connections and update Docker setup by @dieter-medium
 
 ## [0.1.1] - 2025-04-01
 
-### Added
+### 🚀 Added
 
 - Docker Compose setup with Nginx for authentication examples
 - Sample configurations for different authentication methods:
@@ -10,7 +36,7 @@
     - Cookie-based authentication
     - API key header authentication
 
-### Fixed
+### 🐛 Fixed
 
 - HTTP cookie handling issues
 

data/README.md

@@ -1,3 +1,8 @@
+[![Build Status](https://github.com/dieter-medium/bidi2pdf/actions/workflows/ruby.yml/badge.svg)](https://github.com/dieter-medium/bidi2pdf/blob/main/.github/workflows/ruby.yml)
+[![Maintainability](https://api.codeclimate.com/v1/badges/6425d9893aa3a9ca243e/maintainability)](https://codeclimate.com/github/dieter-medium/bidi2pdf/maintainability)
+[![Gem Version](https://badge.fury.io/rb/bidi2pdf.svg)](https://badge.fury.io/rb/bidi2pdf)
+[![Test Coverage](https://api.codeclimate.com/v1/badges/6425d9893aa3a9ca243e/test_coverage)](https://codeclimate.com/github/dieter-medium/bidi2pdf/test_coverage)
+
 # Bidi2pdf
 
 Bidi2pdf is a Ruby gem that generates high-quality PDFs from web pages using Chrome's BiDi (BiDirectional) protocol. It
@@ -94,6 +99,7 @@ docker run -it --rm -v ./output:/reports bidi2pdf \
 ### Test it with docker compose
 
 ```bash
+rake build
 docker compose -f docker/docker-compose.yml up -d
 
 # simple example
@@ -108,6 +114,8 @@ docker compose -f docker/docker-compose.yml exec app bidi2pdf render --url=http:
 # cookie example
 docker compose -f docker/docker-compose.yml exec app bidi2pdf render --url=http://nginx/cookie/sample.html --cookie "auth=secret" --wait_window_loaded --wait_network_idle --output /reports/cookie.pdf
 
+# remote chrome example
+docker compose -f docker/docker-compose.yml exec app bidi2pdf render --url=http://nginx/cookie/sample.html --remote_browser_url http://remote-chrome:3000/session --cookie "auth=secret" --wait_window_loaded --wait_network_idle --output /reports/remote.pdf
 
 docker compose -f docker/docker-compose.yml down
 ```
@@ -126,6 +134,8 @@ docker compose -f docker/docker-compose.yml down
 | `--wait_window_loaded` | Wait for the window to be fully loaded. You need to set a variable `window.loaded`. See ./spec/fixtures/sample.html |
 | `--wait_network_idle`  | Wait for network to be idle                                                                                         |
 | `--log_level`          | Log level (debug, info, warn, error, fatal)                                                                         |
+| `--remote_browser_url` | URL of the remote Chrome instance (default: nil)                                                                    |
+| `--default_timeout`    | Default timeout for operations (default: 60 seconds)                                                                |
 
 ## Development
 

data/Rakefile

@@ -14,6 +14,8 @@ task default: %i[spec rubocop]
 require "chromedriver/binary"
 load "chromedriver/Rakefile"
 
+Dir.glob("tasks/*.rake").each { |r| load r }
+
 desc "Run tests with coverage"
 task :coverage do
   ENV["COVERAGE"] = "true"

data/cliff.toml

@@ -0,0 +1,114 @@
+# git-cliff ~ configuration file
+# https://git-cliff.org/docs/configuration
+
+[changelog]
+# template for the changelog header
+header = """
+<!-- generated by git-cliff start -->
+# Changelog\n
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).\n
+"""
+# template for the changelog body
+# https://keats.github.io/tera/docs/#introduction
+body = """
+{%- macro remote_url() -%}
+  https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }}
+{%- endmacro -%}
+
+{% if version -%}
+    ## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
+{% else -%}
+    ## [Unreleased]
+{% endif -%}
+
+{% for group, commits in commits | group_by(attribute="group") %}
+    ### {{ group | upper_first }}
+    {%- for commit in commits %}
+        - {{ commit.message | split(pat="\n") | first | upper_first | trim }}\
+            {% if commit.remote.username %} by @{{ commit.remote.username }}{%- endif -%}
+            {% if commit.remote.pr_number %} in \
+            [#{{ commit.remote.pr_number }}]({{ self::remote_url() }}/pull/{{ commit.remote.pr_number }}) \
+            {%- endif -%}
+    {% endfor %}
+{% endfor %}
+
+{%- if github.contributors | filter(attribute="is_first_time", value=true) | length != 0 %}
+  ## New Contributors
+{%- endif -%}
+
+{% for contributor in github.contributors | filter(attribute="is_first_time", value=true) %}
+  * @{{ contributor.username }} made their first contribution
+    {%- if contributor.pr_number %} in \
+      [#{{ contributor.pr_number }}]({{ self::remote_url() }}/pull/{{ contributor.pr_number }}) \
+    {%- endif %}
+{%- endfor %}\n
+"""
+# template for the changelog footer
+footer = """
+{%- macro remote_url() -%}
+  https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }}
+{%- endmacro -%}
+
+{% for release in releases -%}
+    {% if release.version -%}
+        {% if release.previous.version -%}
+            [{{ release.version | trim_start_matches(pat="v") }}]: \
+                {{ self::remote_url() }}/compare/{{ release.previous.version }}..{{ release.version }}
+        {% endif -%}
+    {% else -%}
+        [unreleased]: {{ self::remote_url() }}/compare/{{ release.previous.version }}..HEAD
+    {% endif -%}
+{% endfor %}
+<!-- generated by git-cliff end -->
+"""
+# remove the leading and trailing whitespace from the templates
+trim = true
+
+[git]
+# parse the commits based on https://www.conventionalcommits.org
+conventional_commits = true
+# filter out the commits that are not conventional
+filter_unconventional = false
+# regex for preprocessing the commit messages
+commit_preprocessors = [
+    # remove issue numbers from commits
+    { pattern = '\((\w+\s)?#([0-9]+)\)', replace = "" },
+]
+# regex for parsing and grouping commits
+commit_parsers = [
+    # ✅ Additions
+      { message = "^[a|A]dd", group = "🚀 Added" },
+      { message = "^[s|S]upport", group = "🚀 Added" },
+      { message = "^.*: add", group = "🚀 Added" },
+      { message = "^.*: support", group = "🚀 Added" },
+
+      # ❌ Removals
+      { message = "^[r|R]emove", group = "🗑️ Removed" },
+      { message = "^.*: remove", group = "🗑️ Removed" },
+      { message = "^.*: delete", group = "🗑️ Removed" },
+
+      # 🐛 Fixes
+      { message = "^test", group = "🐛 Fixed" },
+      { message = "^fix", group = "🐛 Fixed" },
+      { message = "^.*: fix", group = "🐛 Fixed" },
+
+      # ⛔️ Chore & CI commits to skip
+      { message = "^chore\\(release\\): prepare for", skip = true },
+      { message = "^chore\\(deps.*\\)", skip = true },
+      { message = "^chore\\(pr\\)", skip = true },
+      { message = "^chore\\(pull\\)", skip = true },
+      { message = "^chore", skip = true },
+      { message = "^ci", skip = true },
+
+      # 🌀 Catch-All
+      { message = "^.*", group = "🔄 Changed" }
+]
+# filter out the commits that are not matched by commit parsers
+filter_commits = false
+# sort the tags topologically
+topo_order = false
+# sort the commits inside sections by oldest/newest order
+sort_commits = "newest"

data/docker/Dockerfile.chromedriver

@@ -0,0 +1,33 @@
+FROM ruby:3.3
+
+# Install dependencies
+RUN apt-get update && \
+    apt-get install -y \
+    chromium \
+    libglib2.0-0 \
+    libnss3 \
+    libxss1 \
+    libasound2 \
+    libatk-bridge2.0-0 \
+    libgtk-3-0 \
+    libdrm2 \
+    curl \
+    unzip \
+    xvfb \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user
+RUN groupadd -r appuser && useradd -r -g appuser -m -d /home/appuser appuser
+
+COPY ./docker/entrypoint.sh /usr/local/bin/entrypoint.sh
+RUN chmod +x /usr/local/bin/entrypoint.sh
+
+# Set working directory
+WORKDIR /app
+
+# Switch to non-root user
+USER appuser
+
+RUN gem install chromedriver-binary && ruby -e 'require "chromedriver/binary"; puts Chromedriver::Binary::ChromedriverDownloader.update'
+
+CMD ["/usr/local/bin/entrypoint.sh"]

data/docker/docker-compose.yml

@@ -9,6 +9,13 @@ services:
       - ./nginx/htpasswd:/etc/nginx/conf.d/.htpasswd
       - ../spec/fixtures:/var/www/html
 
+  remote-chrome:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.chromedriver
+    ports:
+      - "9092:3000"
+
   app:
     build:
       context: ..

data/docker/entrypoint.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+/home/appuser/.webdrivers/chromedriver --port=3000 --headless --whitelisted-ips="" --allowed-origins="*" --disable-dev-shm-usage --verbose

data/lib/bidi2pdf/bidi/add_headers_interceptor.rb

@@ -5,7 +5,7 @@ module Bidi2pdf
     class AddHeadersInterceptor
       attr_reader :id, :headers
 
-      def initialize(id, headers, client)
+      def initialize(id, headers:, client:)
         @id = id
         @client = client
         @headers = headers.map do |header|

data/lib/bidi2pdf/bidi/auth_interceptor.rb

@@ -5,7 +5,7 @@ module Bidi2pdf
     class AuthInterceptor
       attr_reader :id, :username, :password, :network_ids
 
-      def initialize(id, username, password, client)
+      def initialize(id, username:, password:, client:)
         @id = id
         @client = client
         @username = username

data/lib/bidi2pdf/bidi/client.rb

@@ -6,6 +6,8 @@ require "websocket-client-simple"
 require_relative "web_socket_dispatcher"
 require_relative "add_headers_interceptor"
 require_relative "auth_interceptor"
+require_relative "command_manager"
+require_relative "connection_manager"
 
 module Bidi2pdf
   module Bidi
@@ -21,7 +23,7 @@ module Bidi2pdf
 
         @connected = false
         @connection_mutex = Mutex.new
-        @send_cmd_mutex = Mutex.new
+        @next_id_mutex = Mutex.new
         @connection_cv = ConditionVariable.new
 
         @started = false
@@ -31,192 +33,105 @@ module Bidi2pdf
         return @socket if started?
 
         @socket = WebSocket::Client::Simple.connect(ws_url)
-        @dispatcher = WebSocketDispatcher.new(@socket)
 
-        @dispatcher.on_open { handle_open }
-        @dispatcher.on_message { |data| handle_response_to_cmd(data) }
+        @connection_manager = ConnectionManager.new(logger: Bidi2pdf.logger)
+        @command_manager = CommandManager.new(@socket, logger: Bidi2pdf.logger)
 
-        @dispatcher.start_listening
+        dispatcher.on_open { @connection_manager.mark_connected }
+        dispatcher.on_message { |data| handle_response_to_cmd(data) }
 
+        dispatcher.start_listening
         @started = true
 
         @socket
       end
 
-      def started?
-        @started
-      end
+      def started? = @started
 
       def wait_until_open(timeout: Bidi2pdf.default_timeout)
-        @connection_mutex.synchronize do
-          unless @connected
-            Bidi2pdf.logger.debug "Waiting for WebSocket connection to open"
-            @connection_cv.wait(@connection_mutex, timeout)
-          end
-        end
-
-        raise "WebSocket connection did not open in time" unless @connected
-
-        Bidi2pdf.logger.debug "WebSocket connection is open"
+        @connection_manager.wait_until_open(timeout: timeout)
       end
 
       def send_cmd(method, params = {})
-        next_id.tap do |cmd_id|
-          payload = {
-            id: cmd_id,
-            method: method,
-            params: params
-          }
-
-          Bidi2pdf.logger.debug "Sending command: #{redact_sensitive_fields(payload).inspect}"
-
-          @socket.send(payload.to_json)
-        end
+        @command_manager.send_cmd(method, params)
       end
 
-      # rubocop:disable Metrics/AbcSize
-      def send_cmd_and_wait(method, params = {}, timeout: Bidi2pdf.default_timeout)
+      def send_cmd_and_wait(method, params = {}, timeout: Bidi2pdf.default_timeout, &block)
         timed("Command #{method}") do
-          id = send_cmd(method, params)
-          queue = @pending_responses[id]
-
-          begin
-            response = queue.pop(true)
-          rescue ThreadError
-            response = queue.pop(timeout: timeout)
-          end
-
-          if response.nil?
-            # rubocop:disable Layout/LineLength
-            Bidi2pdf.logger.error "Timeout waiting for response to command #{id}, cmd: #{method}, params: #{redact_sensitive_fields(params).inspect}"
-            # rubocop:enable Layout/LineLength
-
-            raise "Timeout waiting for response to command ID #{id}"
-          end
-
-          raise "Error response: #{response["error"]}" if response["error"]
-
-          result = response
-
-          result = yield response if block_given?
-
-          result
-        ensure
-          @pending_responses.delete(id)
+          @command_manager.send_cmd_and_wait(method, params, timeout: timeout, &block)
         end
       end
 
-      # rubocop:enable Metrics/AbcSize
+      def on_message(&block) = dispatcher.on_message(&block)
 
-      # Event API for external consumers
-      def on_message(&block) = @dispatcher.on_message(&block)
+      def on_open(&block) = dispatcher.on_open(&block)
 
-      def on_open(&block) = @dispatcher.on_open(&block)
+      def on_close(&block) = dispatcher.on_close(&block)
 
-      def on_close(&block) = @dispatcher.on_close(&block)
-
-      def on_error(&block) = @dispatcher.on_error(&block)
+      def on_error(&block) = dispatcher.on_error(&block)
 
       def on_event(*names, &block)
-        names.each do |name|
-          @dispatcher.on_event(name, &block)
-        end
-
-        send_cmd "session.subscribe", { events: names } if names.any?
+        names.each { |name| dispatcher.on_event(name, &block) }
+        send_cmd("session.subscribe", { events: names }) if names.any?
       end
 
-      def remove_message_listener(block) = @dispatcher.remove_message_listener(block)
+      def remove_message_listener(block) = dispatcher.remove_message_listener(block)
 
       def remove_event_listener(*names, &block)
-        names.each do |event_name|
-          @dispatcher.remove_event_listener(event_name, block)
-        end
+        names.each { |event_name| dispatcher.remove_event_listener(event_name, block) }
       end
 
-      def add_headers_interceptor(
-        context:,
-        url_patterns:,
-        headers:
-      )
-        send_cmd_and_wait("network.addIntercept", {
+      def add_headers_interceptor(context:, url_patterns:, headers:)
+        add_interceptor(
           context: context,
-          phases: ["beforeRequestSent"],
-          urlPatterns: url_patterns
-        }) do |response|
-          id = response["result"]["intercept"]
-          Bidi2pdf.logger.debug "Interceptor added: #{id}"
-
-          AddHeadersInterceptor.new(id, headers, self).tap do |interceptor|
-            on_event "network.beforeRequestSent", &interceptor.method(:handle_event)
-          end
-        end
+          url_patterns: url_patterns,
+          phase: "beforeRequestSent",
+          event: "network.beforeRequestSent",
+          interceptor_class: AddHeadersInterceptor,
+          extra_args: { headers: headers }
+        )
       end
 
-      def add_auth_interceptor(
-        context:,
-        url_patterns:,
-        username:,
-        password:
-      )
-        send_cmd_and_wait("network.addIntercept", {
+      def add_auth_interceptor(context:, url_patterns:, username:, password:)
+        add_interceptor(
           context: context,
-          phases: ["authRequired"],
-          urlPatterns: url_patterns
-        }) do |response|
-          id = response["result"]["intercept"]
-          Bidi2pdf.logger.debug "Interceptor added: #{id}"
-
-          AuthInterceptor.new(id, username, password, self).tap do |interceptor|
-            on_event "network.authRequired", &interceptor.method(:handle_event)
-          end
-        end
+          url_patterns: url_patterns,
+          phase: "authRequired",
+          event: "network.authRequired",
+          interceptor_class: AuthInterceptor,
+          extra_args: { username: username, password: password }
+        )
       end
 
       private
 
-      def next_id
-        cmd_id = nil
-
-        @send_cmd_mutex.synchronize do
-          @id += 1
-          cmd_id = @id
-          @pending_responses[cmd_id] = Queue.new
-        end
-
-        cmd_id
-      end
-
-      def handle_open
-        @connection_mutex.synchronize do
-          @connected = true
-          @connection_cv.broadcast
-        end
+      def dispatcher
+        @dispatcher ||= WebSocketDispatcher.new(@socket)
       end
 
       def handle_response_to_cmd(data)
-        if (id = data["id"]) && @pending_responses.key?(id)
-          @pending_responses[id]&.push(data)
-        elsif (data = data["error"])
-          Bidi2pdf.logger.error "Error response: #{data.inspect}"
+        handled = @command_manager.handle_response(data)
+        return if handled
+
+        if data["error"]
+          Bidi2pdf.logger.error "Error response: #{data["error"].inspect}"
         else
           Bidi2pdf.logger.warn "Unknown response: #{data.inspect}"
         end
       end
 
-      def redact_sensitive_fields(obj, sensitive_keys = %w[value token password authorization username])
-        case obj
-        when Hash
-          obj.each_with_object({}) do |(k, v), result|
-            result[k] = if sensitive_keys.include?(k.to_s.downcase)
-                          "[REDACTED]"
-                        else
-                          redact_sensitive_fields(v, sensitive_keys)
-                        end
+      def add_interceptor(context:, url_patterns:, phase:, event:, interceptor_class:, extra_args: {})
+        send_cmd_and_wait("network.addIntercept", {
+          context: context,
+          phases: [phase],
+          urlPatterns: url_patterns
+        }) do |response|
+          id = response["result"]["intercept"]
+          Bidi2pdf.logger.debug "Interceptor added: #{id}"
+
+          interceptor_class.new(id, **extra_args, client: self).tap do |interceptor|
+            on_event(event, &interceptor.method(:handle_event))
           end
-        when Array
-          obj.map { |item| redact_sensitive_fields(item, sensitive_keys) }
-        else
-          obj
         end
       end
     end

data/lib/bidi2pdf/bidi/command_manager.rb

@@ -0,0 +1,82 @@
+# frozen_string_literal: true
+
+module Bidi2pdf
+  module Bidi
+    class CommandManager
+      def initialize(socket, logger:)
+        @socket = socket
+        @logger = logger
+
+        @id = 0
+        @next_id_mutex = Mutex.new
+        @pending_responses = {}
+      end
+
+      def send_cmd(method, params = {})
+        id = next_id
+        payload = { id: id, method: method, params: params }
+
+        @logger.debug "Sending command: #{redact_sensitive_fields(payload).inspect}"
+        @socket.send(payload.to_json)
+
+        id
+      end
+
+      def send_cmd_and_wait(method, params = {}, timeout: Bidi2pdf.default_timeout)
+        id = send_cmd(method, params)
+        queue = @pending_responses[id]
+
+        response = queue.pop(timeout: timeout)
+        raise_timeout_error(id, method, params) if response.nil?
+        raise "Error response: #{response["error"]}" if response["error"]
+
+        block_given? ? yield(response) : response
+      ensure
+        @pending_responses.delete(id)
+      end
+
+      def queue_for(id)
+        @pending_responses[id]
+      end
+
+      def handle_response(data)
+        if (id = data["id"]) && @pending_responses.key?(id)
+          @pending_responses[id]&.push(data)
+        else
+          false
+        end
+      end
+
+      private
+
+      def next_id
+        @next_id_mutex.synchronize do
+          @id += 1
+          @pending_responses[@id] = Thread::Queue.new
+          @id
+        end
+      end
+
+      def redact_sensitive_fields(obj, sensitive_keys = %w[value token password authorization username])
+        case obj
+        when Hash
+          obj.transform_values.with_index do |v, idx|
+            k = obj.keys[idx]
+            sensitive_keys.include?(k.to_s.downcase) ? "[REDACTED]" : redact_sensitive_fields(v, sensitive_keys)
+          end
+        when Array
+          obj.map { |item| redact_sensitive_fields(item, sensitive_keys) }
+        else
+          obj
+        end
+      end
+
+      def raise_timeout_error(id, method, params)
+        # rubocop:disable Layout/LineLength
+        @logger.error "Timeout waiting for response to command #{id}, cmd: #{method}, params: #{redact_sensitive_fields(params).inspect}"
+        # rubocop:enable Layout/LineLength
+        raise "Timeout waiting for response to command ID #{id}"
+      end
+    end
+  end
+end